Dust generation monitoring system and dust generation monitoring device

Abstract

To provide a dust emission monitoring system and a dust emission monitoring device that can perform automatic and real-time dust emission monitoring in a factory and the like.SOLUTION: A dust emission monitoring system is a dust emission monitoring system comprising a dust emission monitoring device for monitoring a dust emission situation based on an image of a camera which captures an area including a dust emission source as an imaging range, wherein: the dust emission monitoring device determines a dust emission rank of the dust emission area based on concentration classification information for indicating a level of concentration of the dust emission area identified by applying a dust emission determination program to the image, and based on area information for showing a size of the dust emission area; the dust emission monitoring device determines a dust emission rank of the dust emission area, and determines whether the dust emission rank is a dust emission rank of a notification target; and the dust emission monitoring device issues a predetermined notification when it is determined that the dust emission rank is the dust emission rank of the notification target.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a dust generation monitoring system and a dust generation monitoring device. [Background technology]

[0002] Dust emissions from chimneys in factories and other facilities need to be reduced from an environmental perspective, and immediate countermeasures are required when dust is generated. To achieve this, constant monitoring is required. Conventionally, the presence or absence of dust was identified by having several workers take turns checking recorded video, but because this is not real-time monitoring, there is a delay in identifying dust generation, and there is also the possibility of dust being overlooked during the video check. Furthermore, due to personnel constraints, it is impossible to monitor all chimneys on a large site in real time.

[0003] Patent Document 1 discloses a technique for detecting dust generation or dust generation by image processing, and Patent Document 2 discloses a technique for restricting factory production when the measured value of soot and smoke emitted from a factory exceeds a control value. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 5-10737 [Patent Document 2] Japanese Patent Application Laid-Open No. 2009-199237 Summary of the Invention [Problem to be solved by the invention]

[0005] Dust monitoring by humans poses challenges such as overlooking dust due to the inability to monitor in real time, personalizing evaluations due to differences in how each person perceives dust, and delays in taking action against dust due to delayed notifications. Furthermore, even with the technologies disclosed in Patent Documents 1 and 2, it is difficult to perform automatic, real-time dust monitoring.

[0006] The present invention has been made in view of the above, and has an object to provide a dust generation monitoring system and a dust generation monitoring device that can automatically monitor dust generation in factories and the like in real time. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, the dust monitoring system of the present invention is a dust monitoring system equipped with a dust monitoring device that monitors the dust situation based on images from a camera that captures an area including a dust source as its shooting range, and the dust monitoring device applies a dust determination program to the image to identify the dust-producing area, and based on concentration classification information indicating the concentration level of the dust-producing area and area information indicating the size of the dust-producing area, determines the dust rank of the dust-producing area and determines whether the dust rank is a dust rank that requires notification, and if it is determined that the dust is a dust that requires notification, issues a specified notification.

[0008] Furthermore, in the dust monitoring system according to the present invention, when dust is detected across multiple temporally consecutive images, the dust monitoring device identifies the dust source based on the first image in which dust is first detected, identifies a dust rank indicating the scale of dust based on the second image in which dust is last detected, and determines the continuity of dust based on one or more images present between the first and second images.

[0009] Furthermore, in the dust monitoring system according to the present invention, when the dust monitoring device detects multiple dust occurrences from different dust sources within multiple temporally consecutive images, it determines that the dust occurrence with the longer dust occurrence period is the dust occurrence that should be reported.

[0010] Furthermore, in the dust monitoring system according to the present invention, when multiple dust emissions from different dust sources are detected in multiple temporally consecutive images, the dust monitoring device determines that the dust emitted from the dust source at a lower position is the dust to be notified.

[0011] In order to solve the above-mentioned problems and achieve the object, the dust monitoring device of the present invention is a dust monitoring device that monitors the dust situation based on an image taken by a camera that captures an area including a dust source as its shooting range, and determines the dust rank of the dust-producing area based on concentration classification information indicating the concentration level of the dust-producing area identified by applying a dust determination program to the image and area information indicating the size of the dust-producing area, and if it is determined that the dust rank is a dust rank that should be notified, outputs data indicating that the dust is the target for a specified notification by the notification device. [Effects of the Invention]

[0012] According to the dust monitoring system and the dust monitoring device of the present invention, dust monitoring in a factory or the like can be carried out automatically and in real time. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a block diagram showing a schematic configuration of a dust generation monitoring system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing an example of a dust monitoring range in the dust monitoring system according to the embodiment of the present invention. [Figure 3] FIG. 3 is a diagram showing an example of a dust monitoring range in the dust monitoring system according to the embodiment of the present invention. [Figure 4] FIG. 4 is an explanatory diagram for explaining a conventional dust generation detection method. [Figure 5] FIG. 5 is an explanatory diagram for explaining three-stage authentication by the dust generation monitoring system according to the embodiment of the present invention. [Figure 6] FIG. 6 is a diagram showing a case where dust is detected across a plurality of temporally consecutive images and feedback correction is not performed. [Figure 7] FIG. 7 is a diagram showing a case where feedback correction is performed when dust is detected across a plurality of temporally consecutive images. [Figure 8]FIG. 8 is a flowchart showing the flow of a dust generation monitoring method executed by a dust generation monitoring system according to an embodiment of the present invention. [Figure 9] FIG. 9 is an embodiment of a dust generation monitoring system and a dust generation monitoring device according to the present invention, and is a graph showing an example of the dust generation detection rate and false detection rate of the present invention. [Figure 10] FIG. 10 is an embodiment of the dust generation monitoring system and dust generation monitoring device according to the present invention, and is a graph showing an example of the working hours of workers before and after the introduction of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0014] A dust monitoring system and a dust monitoring device according to an embodiment of the present invention will be described with reference to the drawings. Note that the components in the following embodiments include those that are easily replaceable by those skilled in the art, or those that are substantially identical.

[0015] (Dust monitoring system) The dust monitoring system according to the embodiment is a system for monitoring the state of dust generation inside and outside a factory such as a steel mill. The dust monitored by the dust monitoring system includes smoke, soot, water vapor, etc., generated from chimneys and the like in the factory.

[0016] As shown in Fig. 1, the dust monitoring system 1 includes multiple cameras 10, an AI (Artificial Intelligence) server 20, a data server 30, and a mail server 40. The cameras 10, the AI ​​server 20, the data server 30, and the mail server 40 all have communication functions and are configured to be able to communicate with each other via a network N. This network N is configured, for example, from an internet network, a mobile phone network, WiFi (Wireless Fidelity, registered trademark), BLE (Bluetooth (registered trademark)), etc. Furthermore, the dust monitoring device according to the embodiment is configured from the AI ​​server 20, or the AI ​​server 20 and the mail server 40, which are components of the dust monitoring system 1.

[0017] The camera 10 is installed inside or outside a factory such as a steel mill, and captures images of an area including one or more dust sources within its imaging range. The camera 10 is realized by an imaging device equipped with, for example, a general CCD (Charge Coupled Device) sensor or a CMOS (Complementary Metal Oxide Semiconductor) sensor.

[0018] In dust monitoring using cameras 10, for example, as shown in FIG. 2, cameras 10 are installed on the factory premises facing in multiple directions and continuously capture images. In FIG. 3, (a) is the capture range of camera 10 facing north in FIG. 2, (b) is the capture range of camera 10 facing the center in FIG. 2, and (a) is the capture range of camera 10 facing south in FIG. 2. Of the capture ranges shown in FIG. 3, the range that includes a chimney or other source of dust is the dust monitoring range. In addition, in FIGS. 2 and 3, indications such as "**CO (extrusion)," "**chimney," and "**CDQ" indicate facilities that may be sources of dust. In addition, "CDQ" refers to a coke dry quenching facility.

[0019] Since the installation position of the camera 10 is always fixed, the position coordinates of the dust source, such as a chimney, are also known in advance on the system side (AI server 20 side). In addition, the images taken by the camera 10 are sequentially transmitted to the AI ​​server 20 via the network N.

[0020] The AI ​​server 20 monitors the dust generation status based on images captured by the camera 10. This AI server 20 is realized by a general-purpose computer such as a workstation or a personal computer, or a server device located on the cloud. The AI ​​server 20 may also be installed in a factory. The AI ​​server 20 also includes a dust generation determination unit 21.

[0021] The dust generation determination unit 21 determines whether or not the dust generation is a dust that should be notified based on the density and area of ​​the dust region identified by applying a dust generation determination program to the image captured by the camera 10. If the dust generation determination unit 21 determines that the dust generation is a dust that should be notified, it outputs data indicating that the dust generation is a dust that should be notified by the mail server 40 that functions as a notification device to the mail server 40. The dust generation determination program is an AI model that learns about dust generation by deep learning using, for example, several thousand dust generation images (images that include dust) as training data.

[0022] In the AI ​​model, for example, several thousand dust images are classified into large, medium, and small dust scales (hereinafter referred to as "dust ranks") based on the area and concentration of the dust region, and each dust image is learned as training data along with the dust rank (e.g., large, medium, and small). Then, the dust determination unit 21 applies the above-mentioned dust determination program to an image newly captured by the camera 10, thereby determining whether the dust contained in the image is dust that requires notification and whether the dust level is large, medium, or small. An example of "dust that requires notification" is dust that has a dust level of "medium" or higher.

[0023] Furthermore, the AI ​​model may classify, for example, several thousand dust images into density classes (for example, dark, normal, and light), and learn each dust image together with this density class information as training data. In this case, the dust determination unit 21 applies the above-described dust determination program to an image newly captured by the camera 10, thereby determining whether or not dust contained in the image is dust to be notified, and which of the above-described densities it has.

[0024] Note that the area of ​​a dust-generating region can be recognized by using a segmentation AI model to label the pixels in the dust-generating portion of the image and quantifying the number of pixels, or by using an object detection technique to extract the dust-generating region in the image and quantifying the number of pixels. It is also possible to determine whether the dust level falls into large, medium, or small based on the dust concentration and the area of ​​the dust-generating region. Note that the classification of dust levels into "large, medium, and small" is just one example, and the level may be classified into two or fewer, or four or more, as necessary.

[0025] Here, consider a case where a single image contains multiple dust sources (e.g., chimneys), as shown in Fig. 4. In the figure, dust is located above multiple dust sources, so if an attempt is made to identify both the dust source and the dust rank from a single image, it may not be possible to accurately identify the dust source. Therefore, it is preferable that the dust determination unit 21 identify the dust source, dust rank, etc., based on multiple images.

[0026] In this case, when dust is detected across multiple temporally consecutive images by the above-mentioned dust generation determination program, the dust generation determination unit 21 identifies the dust source based on the first image in which dust generation was first detected, and identifies the dust generation rank indicating the scale of dust generation based on the second image in which dust generation was last detected.The dust generation determination unit 21 then determines the continuity of dust generation based on one or more images present between the first and second images.

[0027] The dust generation determination unit 21 recognizes dust generation by dividing it into early, middle, and late stages, as shown in FIG. 5, for example. That is, the dust generation determination unit 21 identifies the dust generation source based on an image of the early stage of dust generation. The dust generation determination unit 21 also identifies the dust generation rank (for example, large, medium, or small) based on an image of the later stage of dust generation. The dust generation rank can be identified based on the area and density of the dust generation region. The dust generation determination unit 21 also determines the continuity of dust generation based on an image of the middle stage of dust generation. In this way, the process of identifying the dust generation source, the continuity of dust generation, and the dust generation rank based on images of the early, middle, and late stages of dust generation is defined as "three-stage authentication" in this embodiment.

[0028] For convenience of explanation, Fig. 5 shows only the image corresponding to the latter part of the dust generation period (the second image described above), but for example, an "image of the early stage of dust generation" used to identify the dust source does not include dust generation in the middle or later stages. Similarly, an "image of the middle stage of dust generation" used to determine the continuity of dust generation does not include dust generation in the later stage.

[0029] Furthermore, for example, as shown in Figure 6, when multiple dust sources (e.g., chimneys) are included in one image, the actual dust source is "6CO extrusion," but since the dust-emitting area also overlaps with "56CDQ," "56CDQ" may be identified as the dust source. In the same figure, for example, after dust is detected in both "6CO extrusion" and "56CDQ," "56CDQ" may be identified as the dust source.

[0030] Therefore, it is preferable that the dust generation determination unit 21 retains logic and performs feedback correction when multiple dust occurrences are detected using the above-mentioned dust generation determination program. Note that "retaining logic" means that when multiple dust occurrences are detected in one image, for example, the detection results of the multiple dust occurrences are retained. In this case, when multiple dust occurrences from different dust sources are detected in multiple temporally consecutive images, the dust generation determination unit 21 determines that the dust occurrence with the longer dust occurrence period is the dust occurrence that should be reported.

[0031] 7, for example, when multiple dust particles are detected in an image, if the interval between the two (two dust particles) is within a predetermined time (for example, one minute), the dust generation determination unit 21 retains logic that indicates that dust particles have been detected from both (see (1) in the figure). Then, after the dust generation period of "56CDQ" has ended, the dust generation determination unit 21 determines that the dust generated by "6CO extrusion" with the longest dust generation period (dust generation during dust generation period X) is dust that should be reported (see (2) in the figure).

[0032] Furthermore, when multiple dust emissions from different dust sources ("6CO extrusion", "56CDQ") are detected in multiple temporally consecutive images, as shown in Fig. 7, for example, the dust generation determination unit 21 determines that the dust (dust emission in dust generation period X) generated from the dust source located lower ("6CO extrusion") is the dust to be reported. In this way, when multiple dust emissions from different dust sources are detected, the process of identifying the actual dust source is defined as "feedback correction" in this embodiment.

[0033] The data server 30 is realized by a general-purpose computer such as a workstation or a personal computer, or a server device located on the cloud. The data server 30 may also be installed in a factory. Although the data server 30 and the AI ​​server 20 are illustrated as separate components in FIG. 1, the data server 30 may also be provided within the AI ​​server 20. The data server 30 also includes a classification storage unit 31 and a memory unit 32.

[0034] The classification storage unit 31 classifies and stores the dust generation determination results from the dust generation determination unit 21. This "dust generation determination result" is data indicating that the dust generation is the target for a predetermined notification by the mail server 40 functioning as a notification device. The dust generation determination results from the dust generation determination unit 21 include, for example, an image containing dust (dust generation image), the dust generation source, the dust generation level (e.g., large, medium, small), the dust generation area, and the dust generation concentration classification (e.g., dark, normal, light). The classification storage unit 31 classifies the above-mentioned dust generation determination results and stores them in the memory unit 32.

[0035] The storage unit 32 is configured with recording media such as an EPROM (Erasable Programmable ROM), a hard disk drive (HDD), and removable media. Examples of removable media include disk recording media such as a USB (Universal Serial Bus) memory, a CD (Compact Disc), a DVD (Digital Versatile Disc), and a BD (Blu-ray (registered trademark) Disc). The storage unit 32 can store an operating system (OS), various programs, various tables, various databases, and the like. The storage unit 32 stores, for example, the dust generation determination result from the dust generation determination unit 21.

[0036] The mail server 40 is implemented by a general-purpose computer such as a workstation or a personal computer, or a server device located on a cloud. The mail server 40 may also be installed in a factory. The mail server 40 includes a notification unit 41.

[0037] When the dust determination unit 21 determines that the dust contained in the image is dust that is to be notified (for example, dust with a dust level of "medium" or higher), the notification unit 41 acquires the dust determination result from the dust determination unit 21. Then, the notification unit 41 issues a predetermined notification based on the acquired dust determination result. Examples of the "predetermined notification" include sending an email to relevant parties, issuing an alarm to relevant parties, etc. Furthermore, the notification unit 41 may issue a predetermined notification when the number of images containing dust that is to be notified reaches a predetermined threshold.

[0038] In the dust monitoring system and dust monitoring device according to the embodiment having the above configuration, consider a case where, for example, one dust source is monitored by one camera 10. In this case, one camera 10 is installed so that one dust source whose position coordinates are known is included in the imaging range, and then the AI ​​server 20 captures images at a rate of, for example, one image per second. Next, the dust determination unit 21 of the AI ​​server 20 uses a dust determination program to detect dust in the images. When dust is detected, for example, the concentration and scale of the dust are calculated and identified as a dust generation rank.

[0039] Next, the determination results, including the images in which dust was detected and the dust rank, are stored in the data server 30, and when, for example, the number of images containing dust to be notified reaches a predetermined threshold, the notification unit 41 of the mail server 40 sends an email to the relevant parties requesting them to take corrective action. By performing this process, dust generation can be suppressed, and the environmental load can be reduced.

[0040] In addition, consider a case where, for example, two or more dust sources are monitored by a single camera 10 in the dust monitoring system and dust monitoring device according to the embodiment having the above-described configuration. In this case, the single camera 10 is installed so that two or more dust sources whose position coordinates are known are included in the imaging range, and then the AI ​​server 20 captures images at a rate of, for example, one image per second. Next, the dust generation determination unit 21 of the AI ​​server 20 uses a dust generation determination program to detect dust generation in the images. When dust generation is detected, the dust generation images are tracked, for example, until the dust generation disappears, and the images are classified into early, middle, and late stages of dust generation.

[0041] Next, the dust generation determination unit 21 determines the dust generation source from the images of the dust generation stage, the continuity of dust generation from the images of the middle stage of dust generation, and the dust generation rank from the images of the later stage of dust generation (three-stage authentication). Because the installation position of the camera 10 is fixed, the position coordinates of the multiple dust generation sources in the images are also known in advance. Furthermore, the continuity of dust generation between multiple images can be determined, for example, by whether or not the dust generation areas between the images overlap. Furthermore, the dust generation rank can be determined based on the range of dust generation from the start of dust detection until the dust generation disappears.

[0042] Furthermore, when dust generation is detected in two or more places for a preset dust source, the dust generation determination unit 21 performs the above three-stage authentication for each dust generation, and adopts, for example, the dust generation source with the longest time since dust generation as the dust generation source for this time (feedback correction). In other words, when dust generation is detected, the dust generation determination unit 21 performs three-stage authentication and feedback correction for a group of images (tracked image group) from the start of dust generation detection to the end of dust generation.

[0043] Next, the dust generation images and the determination results including the dust generation rank are stored in the data server 30, and when, for example, the number of images containing dust to be notified reaches a predetermined threshold, the notification unit 41 of the mail server 40 sends an email to the relevant parties requesting them to take corrective action. By performing such processing, dust generation can be suppressed, and the environmental load can be reduced.

[0044] In this way, the dust generation monitoring system and dust generation monitoring device according to the embodiment detects dust generation using a pre-trained dust generation determination program and performs predetermined post-processing (three-step authentication, feedback correction) as necessary, thereby enabling automatic real-time monitoring of dust generation in factories and the like.

[0045] (Dust generation monitoring method) The flow of the dust generation monitoring system and the dust generation monitoring method executed by the dust generation monitoring device according to the embodiment will be described with reference to FIG.

[0046] First, the dust generation determination unit 21 reads an image captured by the camera 10 (step S11). Next, the dust generation determination unit 21 detects dust generation in the image using a dust generation determination program (step S12).

[0047] Next, the dust generation determination unit 21 identifies the dust generation source based on the image of the early stage of dust generation (step S13). Next, the dust generation determination unit 21 determines the continuity of dust generation based on the image of the middle stage of dust generation (step S14). Next, the dust generation determination unit 21 identifies the dust generation rank based on the image of the later stage of dust generation (step S15). The order of steps S13 to S15 is not particularly limited, and may be performed in an order different from that shown in FIG. 8.

[0048] Next, in step S12, if dust generation is detected in two or more locations for a preset dust source, the dust generation determination unit 21 performs feedback correction of the dust source (step S16). Next, the classification storage unit 31 classifies the dust generation determination results from steps S12 to S16 and stores them in the memory unit 32 (step S17). Next, the notification unit 41 sends an email to relevant parties informing them of, for example, the time of dust generation, the dust source, and the dust generation rank (step S18), and this process is completed.

[0049] (Example) An embodiment of a dust generation monitoring system and a dust generation monitoring device according to the present invention will be described with reference to FIGS.

[0050] 9 shows an example of the dust detection rate and false detection rate before and after the introduction of the present invention. In the figure, the vertical axis represents the detection rate (%) and false detection rate (%), and the horizontal axis represents the dust source.

[0051] The three bar graphs in Figure 9(a) show, from left to right, the dust detection rate for Invention 1 (before the introduction of three-step authentication and feedback correction), Invention 2 (after the introduction of three-step authentication), and Invention 3 (after the introduction of three-step authentication and feedback correction). The "detection rate" was calculated by dividing the number of dust particles detected by the system by the number of dust particles detected by humans by 100. As shown by the bold line in Figure 9, the target detection rate is 100%, and the closer the detection rate is to 100%, the higher the performance (the more accurately dust particles can be detected). As shown in the rightmost column of Figure 9 (the "average" column), the methods of Inventions 2 and 3 have detection rates closer to the target value than Invention 1, demonstrating higher performance. While Invention 1 may have a detection rate far from the target value (high false positives) depending on the dust source, false positives are a safe bet, and dust detection is better than no detection at all.

[0052] The three bar graphs in Figure 9(b) show, from left to right, the false detection rate of dust for Invention 1 (before the introduction of three-step authentication and feedback correction), Invention 2 (after the introduction of three-step authentication), and Invention 3 (after the introduction of three-step authentication and feedback correction). The "false detection rate" was calculated by (number of false detections of dust by the system) / (number of dust detections by humans + number of dust detections by the system) × 100. As shown by the bold line in Figure 9, the target value for the false detection rate is 20%, and a false detection rate lower than 20% indicates higher performance (less likely to cause false detection of dust). As shown in the rightmost column of Figure 9 (the "average" column), the methods of Inventions 2 and 3 have false detection rates lower than the target value. It can also be seen that the methods of Inventions 2 and 3 eliminate bias in the false detection rate for each dust source compared to Invention 1. In the present invention 1, depending on the dust source, the false detection rate may be far from the target value (there may be many false detections), but the false detection itself is on the safe side, and performing dust detection is better than not performing it at all.

[0053] Figure 10 shows an example of a dust monitoring system and dust monitoring device according to the present invention, showing an example of worker working hours before and after the introduction of the present invention. Worker working hours consist of, for example, the total time required to "check for large and medium-rank dust," the time required to "contact relevant departments," and the time required to "check for small-rank dust." As shown in the figure, by introducing the present invention, dust monitoring can be automated, and working hours have been reduced by 2.0 hours per day.

[0054] The dust monitoring system and dust monitoring device according to the present invention have been specifically described above using the preferred embodiment and examples, but the scope of the present invention is not limited to these descriptions and should be broadly interpreted based on the claims. It goes without saying that various changes and modifications based on these descriptions are also included in the scope of the present invention. [Explanation of symbols]

[0055] 1. Dust monitoring system 10 Camera 20 AI Server 21 Dust generation determination unit 30 Data Server 31 Classification storage section 32 Storage section 40 Mail Server 41 Information Department

Claims

1. A dust generation monitoring system including a dust generation monitoring device that monitors the state of dust generation based on an image captured by a camera that captures an area including a dust source as its imaging range, The dust generation monitoring device is The apparatus is provided with a dust generation determination program that has been trained as training data using a plurality of dust generation images together with density classification information that indicates the density level of the dust generation area, applying the dust generation determination program to the image captured by the camera to identify a dust generation region in the image captured by the camera and to identify a density classification of the dust generation region; digitizing the number of pixels in the specified dust-generating region to calculate the area of ​​the dust-generating region; determining a dust generation rank of the dust-generating region based on the concentration class of the specified dust-generating region and the calculated area of ​​the dust-generating region, and determining whether the dust generation rank is a dust generation rank to be notified; When it is determined that the dust is a dust to be notified, a predetermined notification is made. Dust monitoring system.

2. When dust generation is detected across a plurality of temporally consecutive images, the dust generation monitoring device identifies the dust source based on a first image in which dust generation is first detected, identifies a dust generation rank indicating the scale of dust generation based on a second image in which dust generation is last detected, and determines the continuity of dust generation based on one or more images present between the first image and the second image. The dust monitoring system according to claim 1 .

3. When a plurality of dust occurrences from different dust sources are detected in a plurality of temporally consecutive images, the dust occurrence monitoring device determines that the dust occurrence with the longer dust occurrence period is the dust occurrence to be notified. The dust monitoring system according to claim 1 .

4. When a plurality of dust emissions from different dust sources are detected in a plurality of temporally consecutive images, the dust monitoring device determines that the dust generated from the dust source at a lower position is the dust to be notified. The dust monitoring system according to claim 1 .

5. A dust generation monitoring device that monitors the state of dust generation based on an image captured by a camera that captures an area including a dust source as its imaging range, The apparatus is provided with a dust generation determination program that has been trained as training data using a plurality of dust generation images together with density classification information that indicates the density level of the dust generation area, applying the dust generation determination program to the image captured by the camera to identify a dust generation region in the image captured by the camera and to identify a density classification of the dust generation region; digitizing the number of pixels in the specified dust-generating region to calculate the area of ​​the dust-generating region; A dust generation monitoring device that determines the dust generation rank of the dust generation region based on the concentration category of the specified dust generation region and the calculated area of ​​the dust generation region.

Images